6 papers
Forgetting Without Restarting: Execution-State Unlearning for Stateful LLM Agents
Chao Yao, Yangbo Wei, Zhen Huang +5
Long-running LLM agents are stateful: beyond the transcript they accrete compressed summaries, plaintext memory, pending tool plans, and, under every serving API, a KV cache. Yet t…
PCBnet: A Dataset and Automatic Construction of SPICE Netlists from Schematic Images
Zhen Huang, Yuhao Gao, Yuzhi Liu +15
Printed circuit boards (PCBs) are fundamental to modern electronic systems, yet AI-driven PCB design automation remains constrained by the lack of large-scale paired schematic-netl…
SkillSmith: Co-Evolving Skills and Tools for Self-Improving Agent Systems
Yangbo Wei, Zhen Huang, Shaoqiang Lu +4
Recent self-evolving agents have shown that skills can be discovered, refined, and accumulated through execution. However, existing skill-evolution frameworks typically assume a fi…
Therm-FM: Foundation Model is ALL YOU NEED for 3D-ICs Thermal Simulation
Zhen Huang, Haiyang Xin, Wenkai Yang +6
Data-driven thermal predictors for 3D-ICs are often trained from scratch for each chip design using many high-fidelity finite-element simulations, leading to high data-generation c…
Self-Attention to Operator Learning-based 3D-IC Thermal Simulation
Zhen Huang, Hong Wang, Wenkai Yang +6
Thermal management in 3D ICs is increasingly challenging due to higher power densities. Traditional PDE-solving-based methods, while accurate, are too slow for iterative design. Ma…
VFlow: Discovering Optimal Agentic Workflows for Verilog Generation
Yangbo Wei, Zhen Huang, Huang Li +3
Hardware design automation faces challenges in generating high-quality Verilog code efficiently. This paper introduces VFlow, an automated framework that optimizes agentic workflow…